Josh Rauvola

Drinking with Einstein

Technology EN ↓ Odcinki: 2

AI Engineer by day (U.S. Bank), researcher by night (UChicago), Josh Rauvola sits where building AI meets understanding why it works. Each week, he breaks down the field's most complex topics until they actually click: interpretability, safety, reasoning models, agents, and more. No hype. No jargon. Just clarity. This podcast exists because there's too much snake oil on one side and too many PhD-level papers on the other. So grab a drink, and let's make sense of the machines we're building together. New episodes weekly—15 to 20 minutes each.

Koniecznie odwiedź stronę podcastu i wesprzyj twórcę: podcasters.spotify.com

Autor

Josh Rauvola

Kategoria

Technology

Strona podcastu

podcasters.spotify.com

Ostatni odcinek

9 lut 2026

Gdzie słuchać?

Podcasty w aplikacji Replaio Radio Już wkrótce

Podcasty trafią do aplikacji już wkrótce. Zainstaluj teraz i jako pierwszy zobacz nowe podejście do podcastów

Zainstaluj za darmo Android prawie 10 mln pobrań · ocena 4,8 iOS niedługo

Odcinki

From Visualizations to Circuits: The Origins of the Glass Box (The Glass Box Pt. 2) 09.02.2026 23:52

Is AI just a "giant math soup" that happens to work, or is it a machine with parts we can understand? In Part 2 of The Glass Box series, we dig into the origin story of Mechanistic Interpretability. We trace the 7-year arc from the first "camera" that let us see inside a neural network (Zeiler & Fergus, 2013) to the "microscope" of Feature Visualization (Olah et a...

Reading the Mind of the Machine (The Glass Box Pt. 1) 20.01.2026 15:46

We have spent the last decade studying AI like psychologists, observing behavior and guessing at thoughts. It’s time to become neurosurgeons. In this debut episode, AI Engineer Josh Rauvola introduces Mechanistic Interpretability : the emerging science of cracking open neural networks to map the specific circuits inside. We break down how labs like Anthropic, OpenAI, and DeepMind are moving from &...